© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16026
    Prev
    Next
    INDEX
    Explanations

    elements related to navigation and links within a webpage structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "leap" or "leaps" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.55
     nakalista
    -0.47
    featureID
    -0.45
    EDEFAULT
    -0.39
    MessageOf
    -0.37
    cshtml
    -0.36
     onPostExecute
    -0.36
     onOptions
    -0.36
    scriptcase
    -0.34
     tyn
    -0.34
    POSITIVE LOGITS
     jump
    2.73
     Jump
    2.47
    jump
    2.39
     jumps
    2.39
    Jump
    2.39
     jumping
    2.38
     jumped
    2.27
     JUMP
    2.22
     leap
    2.22
    跳
    2.16
    Activations Density 0.406%

    No Known Activations